You are provided with a paragraph. Your goal is to automatically identify the…
- User
System: You are provided with a paragraph. Your goal is to automatically identify the most relevant tasks based on the content of the paragraph and generate an example of entailment (if the task conclusion can be logically inferred from the paragraph) and a different example of non-entailment (if it is unclear or the opposite conclusion is true).
Step 1: Read the paragraph carefully. Step 2: Automatically decide which tasks are relevant based on the paragraph’s content. Relevant tasks may include, but are not limited to: - Topic Classification - Risk Classification - Sentiment Classification - Tone Classification - Event Detection - Entity Recognition - Geographical Recognition - Trend Detection - Intent Detection - Sector Identification - Impact Classification - Tense Identification (Past, Present, Future) - Uncertainty Identification
Step 3: For each relevant task you identify, generate two clear and concise examples whose labels match common practices for the task at hand: one for entailment and one for non-entailment. The example should speak about the text at the 3rd person. Step 4: Output the results in the following JSON format:
{ 'relevant_tasks': [ { 'task': , 'examples': [ { 'input': , 'label': 'entailment', }, { 'input': <The non-entailment example (neutral or contradiction) based on the paragraph>, 'label': 'non-entailment', } ] }, ... ] } User: Health and Human Services Secretary Alex Azar said the agency supports the Food and Drug Administration's proposed e-cigarette crackdown. The FDA earlier this week threatened to pull e-cigarettes from shelves if manufacturers do not control teen use. The FDA is specifically ordering five brands — Assistant:
- Assistant
{ 'relevant_tasks': [ { 'task': 'Entity Recognition', 'examples': [ { 'input': 'The paragraph mentions Health and Human Services Secretary Alex Azar.', 'label': 'entailment', }, { 'input': 'The paragraph mentions the Prime Minister of Canada.', 'label': 'non-entailment', } ] }, { 'task': 'Event Detection', 'examples': [ { 'input': 'The paragraph discusses the FDA’s proposed e-cigarette crackdown.', 'label': 'entailment', }, { 'input': 'The paragraph discusses a newly signed international peace treaty.', 'label': 'non-entailment', } ] }, { 'task': 'Intent Detection', 'examples': [ { 'input': 'Alex Azar intends to support the FDA’s effort to regulate e-cigarettes.', 'label': 'entailment', }, { 'input': 'Alex Azar intends to promote the unrestricted sale of e-cigarettes.', 'label': 'non-entailment', } ] }, { 'task': 'Tense Identification', 'examples': [ { 'input': 'The paragraph is discussing events happening in the present.', 'label': 'entailment', }, { 'input': 'The paragraph is discussing events that took place in the distant past.', 'label': 'non-entailment', } ] }, { 'task': 'Risk Classification', 'examples': [ { 'input': 'The paragraph highlights a risk related to teen use of e-cigarettes.', 'label': 'entailment', }, { 'input': 'The paragraph highlights a risk related to physical exercise.', 'label': 'non-entailment', } ] } ] }